Skill389 repo starsupdated 19d ago

benchmark-challenge

This skill identifies unstated assumptions embedded in industry benchmarks and best practices, then systematically negates them to expose hidden constraints and reveal unexplored possibilities. Use it when established standards may be limiting innovation or when you need to understand what foundational beliefs underpin conventional approaches in your field.

View source Repository: de-anthropocentric-research-engine

Install in Claude Code

Copy

git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/benchmark-challenge && cp -r /tmp/benchmark-challenge/skills/benchmark-challenge ~/.claude/skills/benchmark-challenge

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Benchmark Challenge

Identify and negate benchmark assumptions.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent skill.

## Why Subagent

Benchmark challenge requires deep analysis of why a best practice exists, what assumptions it encodes, and what happens when those assumptions are violated. Benefits from dedicated critical focus.

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->